It takes (only) two: adversarial generator-encoder networks
We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the advers...
Asıl Yazarlar: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Materyal Türü: | Conference item |
Baskı/Yayın Bilgisi: |
Association for the Advancement of Artificial Intelligence
2018
|
Benzer Materyaller
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
Yazar:: Ulyanov, D, ve diğerleri
Baskı/Yayın Bilgisi: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
Yazar:: Ulyanov, D, ve diğerleri
Baskı/Yayın Bilgisi: (2016) -
Deep image prior
Yazar:: Ulyanov, D, ve diğerleri
Baskı/Yayın Bilgisi: (2018) -
Deep image prior
Yazar:: Ulyanov, D, ve diğerleri
Baskı/Yayın Bilgisi: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
Yazar:: Chatfield, K, ve diğerleri
Baskı/Yayın Bilgisi: (2011)